Ade20kDataLoader<T>

Models & Types · AiDotNet.Data.Vision.Benchmarks

Loads the ADE20K semantic segmentation dataset.

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → Ade20kDataLoader<T>

How It Works

ADE20K expects:

Features are flattened image pixels Tensor[N, H * W * 3]. Labels are flattened segmentation mask Tensor[N, H * W] with class indices.

Constructors

Constructor Summary
Ade20kDataLoader(Ade20kDataLoaderOptions options)

Properties

Property Summary
int FeatureCount { get; }
int OutputDimension { get; }
int TotalCount { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
ValueTuple<IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>> Split(double trainRatio, double validationRatio, int? seed)